© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64430
    Prev
    Next
    INDEX
    Explanations

    class extends other class

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (integer literals or standalone digit sequences) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    なんですよ
    -1.66
    なんですね
    -1.50
    なのだ
    -1.28
    だったので
    -1.25
    mitsubishi
    -1.24
    så
    -1.23
     údaj
    -1.22
    inį
    -1.19
     Czy
    -1.18
    বং
    -1.18
    POSITIVE LOGITS
     extends
    3.30
     is
    3.06
     was
    2.30
     extending
    1.60
     extend
    1.50
    extends
    1.50
     other
    1.42
     continues
    1.39
     has
    1.38
     goes
    1.38
    Activations Density 0.022%

    No Known Activations